# GMMLU leaderboard

Multilingual benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/multilingual-gmmlu

Global MMLU. Every model the catalog carries a published GMMLU value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Multilingual |
| Measure | Average accuracy |
| Tasks | Knowledge questions across 42 languages |
| Difficulty | Multilingual knowledge |
| Published by | [Global MMLU: Understanding and addressing cultural and linguistic biases in multilingual evaluation](https://arxiv.org/abs/2412.03304) |

MMLU-style knowledge evaluation across 42 high- and low-resource languages.

## GMMLU ranking

5 models with a published GMMLU value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Average accuracy | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Fable 5.2](https://modelscale.dev/models/claude-fable-5-2) | Anthropic | 96.0 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Claude Opus 5.5](https://modelscale.dev/models/claude-opus-5-5) | Anthropic | 94.3 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Claude Fable 5.1](https://modelscale.dev/models/claude-fable-5-1) | Anthropic | 94.0 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Claude Opus 5](https://modelscale.dev/models/claude-opus-5) | Anthropic | 92.5 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Claude Sonnet 5.5](https://modelscale.dev/models/claude-sonnet-5-5) | Anthropic | 92.1 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
